作者: Esteban Vera , Luis Mancera , S. Derin Babacan , Rafael Molina , Aggelos K. Katsaggelos
关键词:
摘要: In this paper, we propose a novel algorithm for image reconstruction from compressive measurements of wavelet coefficients. By incorporating independent Laplace priors on separate sub-bands, the inhomogeneity coefficient distributions and therefore structural sparsity within images are modeled effectively. We model problem by adopting Bayesian formulation, develop fast greedy algorithm. Experimental results demonstrate that performance proposed is competitive with state-of-the-art methods while outperforming them in terms running times.